| Paper | Code | rFID | PSNR | SSIM | LPIPS | ModelName | ReleaseDate |
|---|---|---|---|---|---|---|---|
| High-Resolution Image Synthesis with Latent Diffusion Models | ✓ Link | 1.07 | 26.86 | SD-VAE (16x16) | 2021-12-20 | ||
| MGVQ: Could VQ-VAE Beat VAE? A Generalizable Tokenizer with Multi-group Quantization | ✓ Link | 1.59 | 28.27 | 0.844 | 0.092 | MGVQ (16x16x4) | 2025-07-14 |
| Open-MAGVIT2: An Open-Source Project Toward Democratizing Auto-regressive Visual Generation | ✓ Link | 4.18 | 23.91 | Open-Magvit2 (16x16) | 2024-09-06 | ||
| Autoregressive Model Beats Diffusion: Llama for Scalable Image Generation | ✓ Link | 5.59 | 23.90 | 0.720 | 0.177 | LlamaGen (16x16) | 2024-06-10 |
| Taming Transformers for High-Resolution Image Synthesis | ✓ Link | 5.95 | 22.91 | VQGAN (16x16) | 2020-12-17 | ||
| Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction | ✓ Link | 9.85 | 21.79 | VAR (16x16) | 2024-04-03 |